MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
Progressor is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
97/100
trust score
165
downloads a day
local
runs on your machine
873
downloads in 30d
What it does
Keeps an AI coding agent on its plan across context compression, with a live local dashboard.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user progressor-mcp '--' npx -y progressor-mcp
# 2 — ask your agent for something these tools do
# get_status, get_item, add_goal and 17 more
Progressor costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Progressor as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user progressor-mcp '--' npx -y progressor-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
20 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Compact summary of this Session's Goal, current Task, open Detour, next Task and the Developer's Standing Instructions. Call it at the start of every conversation and after context compression.
No parameter schema on file.
Look up one Goal, Task, Detour, Idea or Standing Instruction by its ref (progressor://<goal>/<item>, or progressor://roadmap/<idea or instruction>), with its file and line. Use it when the Developer pastes a ref or you need one item's details; for where the work stands overall, use get_status.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref | string | yes | A ref such as progressor://login/t2 or progressor://roadmap/i1. |
Add a Goal to the end of the Roadmap, with an optional Task list and Outcome. Does not claim it. A title another Goal already has is refused unless allow_duplicate is set. To record work already finished, set done on the Goal and on every Task.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | A few words naming the Goal, such as 'Ship OAuth login'. |
| id | string | no | A short ID for the Goal's refs, such as 'web-ui': lowercase letters, digits and dashes. Made from the title when left out. |
| outcome | string | no | What done looks like, in one sentence, such as 'Users can sign in with Google and stay signed in for 30 days'. |
| tasks | array | no | — |
| allow_duplicate | boolean | no | Add the Goal even though another Goal has the same title. |
| done | boolean | no | Record a Goal that is already finished. Every Task must then have done: true. |
Rename a Goal or set its Outcome. Its ID, refs and Plan File stay the same, and it needs no Claim. To change a Goal's Tasks, claim it and use add_tasks, update_task or drop_task.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| goal | string | yes | The Goal ID, such as 'ship-oauth-login'. |
| title | string | no | The new title. |
| outcome | string | no | The new Outcome; an empty string removes it. |
Move a Goal right before or after another Goal, so the Roadmap lists the work in the order it should happen. Give exactly one of before and after.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| goal | string | yes | The Goal ID, such as 'ship-oauth-login'. |
| before | string | no | The ID of the Goal to move it in front of. |
| after | string | no | The ID of the Goal to move it behind. |
Drop a Goal that will not be done, with the reason; its Plan File stays as a record. Releases this Session's Claim on it. A Goal another running Session holds, or one already done, cannot be dropped. To drop a single Task, use drop_task.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| goal | string | yes | The Goal ID, such as 'ship-oauth-login'. |
| reason | string | yes | Why the Goal will not be done. |
Claim a Goal for this Session, so only this Session works on it. Releases (pauses) any Goal this Session held before. Fails if another running Session holds it. Claiming a done Goal reopens it: its finished Tasks stay done, and add_tasks adds the new work to the same list.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| goal | string | yes | The Goal ID, such as 'ship-oauth-login'. |
| takeover | boolean | no | Take the Goal from another running Session. Only when the Developer asks for it. |
Release this Session's Claim, leaving the Goal paused for a later Session.
No parameter schema on file.
Mark the claimed Goal done and release it, once its Outcome is true and its Tasks are done or dropped. If more work turns up later, claim_goal reopens it.
No parameter schema on file.
Append Tasks to the claimed Goal's plan. For work that is not part of the plan, declare a Detour instead. Set done on a Task that is already finished.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tasks | array | yes | — |
Mark a Task in progress. Only one Task can be in progress at a time.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task | string | yes | The Task ID, such as 't3'. |
Mark a Task of the claimed Goal done, recording the files it touched and, if it changed, the final summary of what it did. Works whether or not the Task was started. For a Task that turned out unnecessary, use drop_task instead; to change a Task without finishing it, use update_task.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task | string | yes | The Task ID, such as 't3'. |
| code | array | no | Files the Task touched, optionally with :line; added to the ones it has. |
| summary | yes | — |
Change a Task's title, summary or files, for instance when the fix turns out different from the plan. Leaves its status alone.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task | string | yes | The Task ID, such as 't3'. |
| title | no | — | |
| summary | yes | — | |
| code | array | no | The Task's files, optionally with :line; replaces the ones it has. |
Drop one Task of the claimed Goal that is no longer needed, with the reason; it stays in the Plan File, struck through. To replace the whole remaining plan, end a Detour with 'recalibrate' instead; to drop the whole Goal, use drop_goal.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task | string | yes | The Task ID, such as 't3'. |
| reason | string | yes | Why the Task is no longer needed. |
Declare that the work is splitting off from the planned Tasks, before doing it. Branches from the current Task. Only one Detour can be open.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | What the Detour does, such as 'Fix flaky token refresh'. |
| reason | string | yes | Why the work has to split off from the plan now. |
End the open Detour. 'merge back': it was small and is done; the plan is unchanged. 'return': go back to the plan, appending tasks for the Detour's intended work if any. 'recalibrate': drop every remaining Task and replace them with tasks.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ending | string | yes | — |
| tasks | array | no | Tasks to append (return) or the new Task list (recalibrate). |
Park a feature or improvement that came up but is not needed for the current Goal, instead of doing it. It goes to the Roadmap's Ideas until the Developer asks for it (promote_idea). For work that is needed now but off the plan, declare a Detour instead.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | The idea in a few words, such as 'Remember-me checkbox'. |
| note | string | no | Context for later: where it came from or why it could matter. |
Turn an Idea into a Task at the end of the claimed Goal, or into a new Goal on the Roadmap.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| idea | string | yes | The Idea ID, such as 'i2'. |
| to | string | yes | — |
Save a lasting rule from the Developer about how you should work in this project, such as 'ask me before recalibrating'. It is shown in every get_status and by the Claude Code hooks. Use it only for rules meant to last; a one-off request is just done, and an idea for later goes to record_idea.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | The rule, in the Developer's words where possible. |
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under GPL-3.0
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Progressor or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 97 / 100
Release 0.6.2 · scanned 22 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score97
Findings2 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digest63753047ab6c80e152f121141e8f5a584ccbcd8a941f4ea55b7d5d30ccb48b35
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (18 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_status | no tags | |
| get_item | no tags | |
| add_goal | no tags | |
| update_goal | no tags | |
| move_goal | no tags | |
| drop_goal | no tags | |
| claim_goal | no tags | |
| release_goal | no tags | |
| complete_goal | no tags | |
| add_tasks | no tags | |
| start_task | no tags | |
| complete_task | no tags | |
| update_task | no tags | |
| drop_task | no tags | |
| start_detour | no tags | |
| end_detour | no tags | |
| add_standing_instruction | no tags | |
| update_standing_instruction | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest63753047ab6c80e1
Scanned2026-10-22
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.6.2. Pin a release below and the command asks for exactly that one.
0.6.2
22 Oct 2026
latestNo release note was published with this version.
0.6.1
21 Oct 2026
No release note was published with this version.
0.6.0
20 Oct 2026
No release note was published with this version.
0.5.2
20 Oct 2026
No release note was published with this version.
0.4.1
19 Oct 2026
No release note was published with this version.
0.4.0
19 Oct 2026
No release note was published with this version.
0.3.0
19 Oct 2026
No release note was published with this version.
0.2.1
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Progressor can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.